© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 120074
    Prev
    Next
    INDEX
    Explanations

    duty of care & sensitivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Teach
    0.57
     OVER
    0.56
     Initialize
    0.52
    ajemen
    0.47
     Puedes
    0.46
     উদাহরণ
    0.46
     Unsere
    0.45
    }\
    0.45
    will
    0.45
     $(
    0.45
    POSITIVE LOGITS
    atorul
    0.51
    丁寧
    0.50
     îm
    0.49
     réglement
    0.49
    ਤ
    0.49
    хия
    0.49
     الشمس
    0.48
    𝕦
    0.48
     naik
    0.47
    ペ
    0.47
    Activations Density 0.000%

    No Known Activations